INDEX

Explanations

phrases related to living spaces like dormitories

oai_token-act-pair · gpt-3.5-turbo

references to living accommodations or housing arrangements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RAY

-0.67

 decisive

-0.61

 Zimbabwe

-0.60

++++++++++++++++

-0.60

SHIP

-0.59

EStream

-0.59

 delegated

-0.59

 undone

-0.59

 Belarus

-0.59

 Mehran

-0.59

POSITIVE LOGITS

itory

1.58

ancy

1.16

ysis

1.10

ulty

1.05

uates

1.02

iott

1.02

iencies

0.98

mers

0.97

 dorm

0.93

itary

0.89

Activations Density 0.012%

phrases related to living spaces like dormitories

references to living accommodations or housing arrangements

No Comments

No Known Activations